INDEX

Explanations

comparative descriptions with emotional or judgmental tones

oai_token-act-pair · gpt-3.5-turbo

modifiers indicating comparison or intensity

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Vs

-0.62

prints

-0.58

atus

-0.58

 Issa

-0.56

 Hath

-0.54

bryce

-0.54

lol

-0.53

instead

-0.53

 Hollow

-0.53

ibel

-0.52

POSITIVE LOGITS

 consequential

0.66

etheless

0.65

interstitial

0.64

vertising

0.61

å§«

0.61

 tempered

0.59

 mosqu

0.58

cffffcc

0.57

 importantly

0.56

 adolesc

0.56

Activations Density 0.525%

comparative descriptions with emotional or judgmental tones

modifiers indicating comparison or intensity

No Comments

No Known Activations